2017 INTERSPEECH INTERSPEECH 2017

Real-Time Modulation Enhancement of Temporal Envelopes for Increasing Speech Intelligibility

Abstract

In this paper, a novel approach is introduced for performing real-time speech modulation enhancement to increase speech intelligibility in noise. The proposed modulation enhancement technique operates independently in the frequency and time domains. In the frequency domain, a compression function is used to perform energy reallocation within a frame. This compression function contains novel scaling operations to ensure speech quality. In the time domain, a mathematical equation is introduced to reallocate energy from the louder to the quieter parts of the speech. This proposed mathematical equation ensures that the long-term energy of the speech is preserved independently of the amount of compression, hence gaining full control of the time-energy reallocation in real-time. Evaluations on intelligibility and quality show that the suggested approach increases the intelligibility of speech while maintaining the overall energy and quality of the speech signal.

🧭 Keyword Pioneer — audio compression
🐣 Hot Topic Early Bird — signal processing
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Speech & Audio